DeepAI AI Chat
Log In Sign Up

Improving Weakly-supervised Object Localization via Causal Intervention

by   Feifei Shao, et al.

The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels. Previous works endeavor to perceive the interval objects from the small and sparse discriminative attention map, yet ignoring the co-occurrence confounder (e.g., bird and sky), which makes the model inspection (e.g., CAM) hard to distinguish between the object and context. In this paper, we make an early attempt to tackle this challenge via causal intervention (CI). Our proposed method, dubbed CI-CAM, explores the causalities among images, contexts, and categories to eliminate the biased co-occurrence in the class activation maps thus improving the accuracy of object localization. Extensive experiments on several benchmarks demonstrate the effectiveness of CI-CAM in learning the clear object boundaries from confounding contexts. Particularly, in CUB-200-2011 which severely suffers from the co-occurrence confounder, CI-CAM significantly outperforms the traditional CAM-based baseline (58.39 in top-1 localization accuracy). While in more general scenarios such as ImageNet, CI-CAM can also perform on par with the state of the arts.


page 1

page 5

page 8


Further Improving Weakly-supervised Object Localization via Causal Knowledge Distillation

Weakly-supervised object localization aims to indicate the category as w...

Improving Weakly Supervised Sound Event Detection with Causal Intervention

Existing weakly supervised sound event detection (WSSED) work has not ex...

Entropy Guided Adversarial Model for Weakly Supervised Object Localization

Weakly Supervised Object Localization is challenging because of the lack...

Causal Intervention for Weakly-Supervised Semantic Segmentation

We present a causal inference framework to improve Weakly-Supervised Sem...

Improved Techniques For Weakly-Supervised Object Localization

We propose an improved technique for weakly-supervised object localizati...

Evaluating Weakly Supervised Object Localization Methods Right

Weakly-supervised object localization (WSOL) has gained popularity over ...

Hierarchical Complementary Learning for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) is a challenging problem wh...